How it works
The solver applies regret-based self-play to two-player Kuhn poker. It reports decision probabilities, game value and exploitability rather than interpreting the behaviour of real players.
Inputs and units
Choose a bounded iteration count. The demonstration uses 200,000 iterations; increasing the count explores convergence for this particular toy game.
What the result contains
A strategy table, estimated game value and exploitability make the computation inspectable. The analytical reference game value is −1/18 for the first player.
Example MCP call
{
"name": "solve_equilibrium",
"arguments": {
"iterations": 200000
}
}Send this tool name and arguments through a connected MCP client. Discover the authoritative input schema with tools/list.
Execution and availability
ScoreCompute exposes this tool through MCP Streamable HTTP. Rust computation runs on a connected worker; the public website and MCP gateway run separately. CUDA is implemented for simulate_pi; the other tools currently run on CPU. Requests are bounded and concurrent work may be refused when capacity is occupied.
Record inputs, assumptions and returned provenance when sharing a result. The public observatory displays software client names and tool activity, without publishing calculation arguments or results.